BlockchainAnalysis

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. The description adds that it reads the issuer's blacklist function directly across chains and that it is free, providing extra context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and front-loaded with the main purpose. Every sentence adds value: what it checks, which chains, result description, and note about being free. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with 2 params and no output schema, the description adequately explains the result (frozen/not frozen at check time) and covers all necessary context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both parameters. The description reinforces and adds format details (e.g., 0x… for EVM) and explicitly lists all chains, adding value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool checks whether USDT/USDC have blacklisted a wallet address on-chain across 9 chains, distinguishing it from sibling tools like check_token_approvals or check_token_security.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Description explains it reads the on-chain freeze status and that it never reports the cause of a freeze, guiding when to use and what not to expect. Does not explicitly mention when not to use, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes read-only behavior, risk-scoring methodology (using BA's entity labels), and flagging of unlimited allowances and stale grants, adding detail beyond annotations. No contradiction with readOnlyHint or openWorldHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences efficiently convey purpose, key features, and constraints ('Read-only. Ethereum only. Free.'). No fluff, front-loaded with core information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Sufficiently covers the tool's output (risk-scored approvals, unlimited allowance flags, stale grants) despite no output schema. Enough context for an agent to understand what it returns and when to use it, given the complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema already fully describes the single parameter (wallet) with pattern and description. The description confirms Ethereum-only usage but adds minimal additional meaning beyond the schema. Baseline 3 due to high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states that the tool lists a wallet's active ERC-20 token approvals on Ethereum, with risk-scoring and flagging of unlimited allowances and stale grants. This distinguishes it from siblings like check_token_security or check_stablecoin_freeze, which focus on different aspects.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Indicates use for assessing a wallet's attack surface and explicitly restricts to Ethereum ('Ethereum only'), providing clear context. However, it does not explicitly state when not to use this tool or suggest alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint and openWorldHint; the description adds that no transaction is sent, it's free, and reports observed facts not verdicts, providing useful behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and informative, but slightly verbose; however, every sentence adds value, earning a high score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity and good schema coverage, the description fully explains the tool's behavior, outputs, and limitations, making it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for token and chain; the description does not add new parameter semantics beyond what is in the schema, so baseline score is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool simulates buy-and-sell to detect honeypots, taxes, impersonation, and mint authority, distinguishing it from sibling tools like check_stablecoin_freeze and check_token_approvals.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for token security checks and lists supported chains, but does not explicitly specify when to use versus alternatives or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint and openWorldHint. Description adds value by explaining data source (issuers' on-chain blacklist events across multiple chains) and stating that each row is a verifiable on-chain fact that never states the cause. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is front-loaded with the main action ('Query the canonical stablecoin freeze ledger') and is structured as a single informative paragraph. It contains necessary details without excessive fluff, though slightly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, description adequately outlines return values as 'verifiable on-chain fact (issuer acted on address at block/time)'. All 5 parameters are documented in schema. Tool complexity is moderate, and description covers key aspects for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already defines each parameter. Description adds minimal extra context (e.g., 'omit all filters for most recent') but does not significantly enhance meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it queries the history of freeze/unfreeze/destroy events, identifies specific issuers and chains, and explicitly distinguishes from sibling tool check_stablecoin_freeze which checks current freeze status. The verb 'Query' and resource 'stablecoin freeze ledger' are specific and non-tautological.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to use check_stablecoin_freeze for current freeze status instead, and notes that omitting all filters returns most recent events. Provides clear when-to-use and when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true and openWorldHint=true. The description adds value by disclosing the paid nature of calls (x402), the combination of data sources, and the output verdict scale with flags. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured paragraph that front-loads the main action and efficiently packs purpose, behavior, coverage, and pricing. It is concise but could be slightly more structured (e.g., bullet points).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description adequately covers what the tool does, the inputs (chain and address), the output (risk verdict with flags), and important context (11 chains, paid via x402). It is comprehensive given the complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for 'chain' (listing specific IDs) and 'address' (format requirement). The description reinforces the chain list and adds context about the assessment combining multiple factors, but it does not significantly add information beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool assesses a wallet's KYT risk, combining sanctions screening, entity classification, risk scores, and cluster context into a single verdict. The verb 'assess' and resource 'wallet's KYT risk' are specific, and it distinguishes itself from siblings like 'screen_address' by emphasizing behavioral risk over a raw label list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on when to use this tool (behavioral risk assessment distinct from raw labels) and notes it is paid per call via x402. However, it does not explicitly state when not to use it or name alternative tools beyond the implied contrast with raw label lists.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true; description adds that it is 'Free,' which is useful behavioral context beyond annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences covering purpose and usage with no wasted words. Front-loaded with the main action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, no-output-schema discovery tool, the description fully covers what the tool does and when to use it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has no parameters, so the description need not add param info; baseline is 4. Description does not address parameters, but none exist.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists BlockchainAnalysis MCP tools, supported chains, and pricing. It explicitly distinguishes itself from sibling tools by being a discovery/prerequisite tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

States explicitly to 'Call this first to discover what the server can do before invoking a tool,' providing clear usage context. No alternatives given, but it's the only discovery tool among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. The description adds that the verdict is 'derived from BA sanctions + entity labels' and that it is 'Paid per call via x402 (USDC).' No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured paragraph that places the core purpose first. It is concise but could be slightly more structured (e.g., bullet points for chains).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description adequately explains return values (verdict, score, confidence, reasons) and provides context about data sources and payment. All aspects are covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions for both 'address' and 'chain'. The description adds context (e.g., 'wallet or contract' for address, list of chains for chain) but does not significantly expand beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it provides 'a normalized verdict (e.g. safe / caution / high_risk) with a 0-100 score, confidence tier, and plain-language reasons,' which is a specific verb-resource pair. It explicitly distinguishes itself from sibling tools 'screen_address' and 'kyt_risk'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly answers the question 'is it safe to interact with this address?' and states it is 'Distinct from raw labels (screen_address) and transactional risk (kyt_risk).' It also lists supported chains and mentions the payment model, providing clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint and openWorldHint. The description adds significant transparency: it reveals the paid-per-call model, the specific label types (sanctions, scam, etc.), threat levels (SAFE→CRITICAL), source, confidence, and supported chains. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences long, front-loaded with the core purpose, and includes all essential details (data source, output, supported chains, costing) without unnecessary words. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given only 2 parameters, no output schema, and rich annotations, the description is complete. It explains the return value (raw labels), costing model, and supported chains. The agent has enough context to use the tool correctly without ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, baseline is 3. The description adds value by clarifying the chain parameter with examples (ETH, BSC, etc.) and noting that the address format must match the chain. This extra context helps the agent understand parameter requirements beyond the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool screens a wallet against a large dataset of entity labels including sanctions, scams, and more. It specifies the output (raw labels with threat levels) and distinguishes itself from sibling tools like check_stablecoin_freeze by focusing on address-level AML screening.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use the tool (to screen an address for various threats) and mentions it works across major EVM chains plus TRON, SOL, BTC. It also notes it's paid per call via x402. However, it doesn't explicitly state when not to use it or directly compare to alternatives, though the context provides sibling tool names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.